Training in progress, step 150, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 871457448
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c19ef8378564ec33e474a3d99da90671e0dae2248ce76b13060cc0696b9432e8
|
3 |
size 871457448
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 443280340
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51d9b75d382fdb80bfb599bea6d0997d929bfbc46afb774fc9e08264f351f171
|
3 |
size 443280340
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ca51295357a6d600fd0c726212784b1970da6cf307dff1168b6e51a8a8255f
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:921ab0de3764126581ec39378879cb5b5f7b00db4d38a319c5350418d3b5b284
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.3348661661148071,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -45,6 +45,21 @@
|
|
45 |
"eval_samples_per_second": 8.485,
|
46 |
"eval_steps_per_second": 0.266,
|
47 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 50,
|
@@ -59,7 +74,7 @@
|
|
59 |
"early_stopping_threshold": 0.0
|
60 |
},
|
61 |
"attributes": {
|
62 |
-
"early_stopping_patience_counter":
|
63 |
}
|
64 |
},
|
65 |
"TrainerControl": {
|
@@ -73,7 +88,7 @@
|
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
-
"total_flos":
|
77 |
"train_batch_size": 4,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.3348661661148071,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.00810307106393323,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 150,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 8.485,
|
46 |
"eval_steps_per_second": 0.266,
|
47 |
"step": 100
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.00810307106393323,
|
51 |
+
"grad_norm": 1.2271238565444946,
|
52 |
+
"learning_rate": 0.000202,
|
53 |
+
"loss": 1.2749,
|
54 |
+
"step": 150
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.00810307106393323,
|
58 |
+
"eval_loss": 1.344261884689331,
|
59 |
+
"eval_runtime": 1837.1269,
|
60 |
+
"eval_samples_per_second": 8.486,
|
61 |
+
"eval_steps_per_second": 0.266,
|
62 |
+
"step": 150
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 50,
|
|
|
74 |
"early_stopping_threshold": 0.0
|
75 |
},
|
76 |
"attributes": {
|
77 |
+
"early_stopping_patience_counter": 1
|
78 |
}
|
79 |
},
|
80 |
"TrainerControl": {
|
|
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
+
"total_flos": 1.295416427544576e+17,
|
92 |
"train_batch_size": 4,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|